mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
928a39d17b
Groq has never supported raw completions anyhow. So this makes it easier to switch it to LiteLLM. All our test suite passes. I also updated all the openai-compat providers so they work with api keys passed from headers. `provider_data` ## Test Plan ```bash LLAMA_STACK_CONFIG=groq \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=groq/llama-3.3-70b-versatile --vision-inference-model="" ``` Also tested (openai, anthropic, gemini) providers. No regressions.
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from llama_stack.models.llama.sku_list import CoreModelId
|
|
from llama_stack.providers.utils.inference.model_registry import build_model_entry
|
|
|
|
MODEL_ENTRIES = [
|
|
build_model_entry(
|
|
"groq/llama3-8b-8192",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"groq/llama-3.1-8b-instant",
|
|
CoreModelId.llama3_1_8b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"groq/llama3-70b-8192",
|
|
CoreModelId.llama3_70b_instruct.value,
|
|
),
|
|
build_model_entry(
|
|
"groq/llama-3.3-70b-versatile",
|
|
CoreModelId.llama3_3_70b_instruct.value,
|
|
),
|
|
# Groq only contains a preview version for llama-3.2-3b
|
|
# Preview models aren't recommended for production use, but we include this one
|
|
# to pass the test fixture
|
|
# TODO(aidand): Replace this with a stable model once Groq supports it
|
|
build_model_entry(
|
|
"groq/llama-3.2-3b-preview",
|
|
CoreModelId.llama3_2_3b_instruct.value,
|
|
),
|
|
]
|